Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/justinthomas2/agentrc/agentsgit clone --depth 1 https://github.com/JustinThomas2/agentrcWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00828 |
| Opus 5 | $0.00000 | $0.00414 |
| Sonnet 5 | $0.00000 | $0.00166 |
| Haiku 4.5 | $0.00000 | $0.00083 |
Grade A, and why
AGENTS scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Justin's Agent Instructions
General Guidelines
- Prefer simple, maintainable solutions over clever abstractions.
- Do not change architecture just for style. Make changes only when they solve a real problem.
- When uncertain, explain the tradeoff before editing.
- For non-trivial changes, make a short plan before implementation.
- For bugs, reproduce the issue before fixing when practical.
- Prefer functional TypeScript patterns over classes unless the project clearly uses classes.
- Always use type annotations where the language supports them (Python type
hints, TypeScript over untyped JavaScript, etc.). Untyped code is
acceptable only where the language offers no typing. Prefer precise types
over escape hatches like
Any(narrow unknown data with runtime checks instead); whether to strictly enforce that is each project's own call. - Avoid regular expressions in code that gets saved, executed, or read by humans; prefer explicit string operations. A one-off regex inside an ad-hoc shell command an agent runs is fine. Committing a regex requires an extremely strong justification - state it in a comment, or don't use one.
- Do not add dependencies without explaining why the existing stack is insufficient.
- Keep responses concise unless Justin asks for deeper explanation.
- Avoid em dashes in prose. Use plain dashes instead.
Project Work Style
- Preserve the user's learning. Do not over-automate when Justin is practicing.
- When Justin is building portfolio/interview projects, prioritize understanding and explain decisions.
- When working autonomously, validate with lint, typecheck, tests, or a runnable smoke test.
Git workflow (personal defaults)
These are my defaults across all projects. If a project's own instructions file (AGENTS.md / CLAUDE.md) defines different conventions, follow the project's.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 71 lines · 0 tokens per session scan A 05f65bfca630
AGENTS is an agent published in the GitHub repository JustinThomas2/agentrc (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 828 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.